A Trustworthy Framework for Skin Cancer Detection Using a CNN with a Modified Attention Mechanism

Su Myat Thwin; Hyun-Seok Park; Soo Hyun Seo

doi:10.3390/app15031067

journal article Open Access Jan 22, 2025

A Trustworthy Framework for Skin Cancer Detection Using a CNN with a Modified Attention Mechanism

Su Myat Thwin

Hyun-Seok Park

Soo Hyun Seo

Applied Sciences Vol. 15 No. 3 pp. 1067 · MDPI AG

View at Publisher Save 10.3390/app15031067

Abstract

The early and accurate detection of skin cancer can reduce mortality rates and improve patient outcomes, but requires advanced diagnostics. The integration of artificial intelligence (AI) into healthcare enables the precise and timely detection of skin cancer. However, significant challenges remain including the difficulty in differentiating visually similar skin conditions and the limitations of diverse, representative datasets. In this study, we proposed DCAN-Net, a novel deep-learning framework designed for the early detection of skin cancer. The model leverages an efficient backbone architecture optimized for capturing diverse skin patterns, utilizing carefully tuned parameters to enhance the discrimination capabilities and refine the extracted features using modified attention modules, thereby prioritizing relevant foreground information while minimizing background noise. Furthermore, the Grad-CAM explainable AI method was employed, highlighting the most salient features within dermatoscopic images. The fused optimal feature representations significantly enhanced the dermatoscopic image analysis. When evaluated on the HAM10000 dataset, DCAN-Net achieved a precision, recall, F1-score, and accuracy of 97.00%, 97.57%, 97.10%, and 97.57%, respectively. Moreover, the application of advanced data augmentation techniques mitigated data imbalance issues and reduced false-positive and false-negative rates across the original and augmented datasets. These findings demonstrate the potential of DCAN-Net for improving clinical outcomes and advancing AI-driven skin cancer diagnostics.

Topics

No keywords indexed for this article. Browse by subject →

References

48

[1]

Alam, T.M., Milhan, M., Atif, M., Wahab, A., and Mushtaq, M. (2019). Cervical cancer prediction through different screening methods using data mining. IJACSA Int. J. Adv. Comput. Sci. Appl. 10.14569/ijacsa.2019.0100251

[2]

Shalhout "Immunotherapy for Nonmelanoma skin cancer: Facts and Hopes" Clin. Cancer Res. (2022) 10.1158/1078-0432.ccr-21-2971

[3]

Mignion "Noninvasive detection of the endogenous free radical melanin in human skin melanomas using electron paramagnetic resonance (EPR)" Free Radic. Biol. Med. (2022) 10.1016/j.freeradbiomed.2022.08.020

[4]

Gururaj "DeepSkin: A deep learning approach for skin cancer classification" IEEE Access (2023) 10.1109/access.2023.3274848

[5]

Tschandl "Comparison of the accuracy of human readers versus machine-learning algorithms for pigmented skin lesion classification: An open, web-based, international, diagnostic study" Lancet Oncol. (2019) 10.1016/s1470-2045(19)30333-x

[6]

American Cancer Society (2022). Key Statistics for Melanoma Skin Cancer, American Cancer Society Center.

[7]

Riaz "A Comprehensive Joint Learning System to Detect Skin Cancer" IEEE Access (2023) 10.1109/access.2023.3297644

[8]

Automated oral cancer identification using histopathological images: A hybrid feature extraction paradigm

M. Muthu Rama Krishnan, Vikram Venkatraghavan, U. Rajendra Acharya et al.

Micron 2012 10.1016/j.micron.2011.09.016

[9]

Skin cancer diagnosis: Leveraging deep hidden features and ensemble classifiers for early detection and classification

G. Akilandasowmya, G. Nirmaladevi, SU. Suganthi et al.

Biomedical Signal Processing and Control 10.1016/j.bspc.2023.105306

[10]

Argenziano "Dermoscopy of pigmented skin lesions—A valuable tool for early" Lancet Oncol. (2001) 10.1016/s1470-2045(00)00422-8

[11]

Kittler "Diagnostic accuracy of dermoscopy" Lancet Oncol. (2002) 10.1016/s1470-2045(02)00679-4

[12]

Javaid, A., Sadiq, M., and Akram, F. (2021, January 12–16). Skin cancer classification using image processing and machine learning. Proceedings of the 2021 International Bhurban Conference on Applied Sciences and Technologies (IBCAST), Islamabad, Pakistan. 10.1109/ibcast51254.2021.9393198

[13]

Yar, H., Abbas, N., Sadad, T., and Iqbal, S. (2021). Lung nodule detection and classification using 2D and 3D convolution neural networks (CNNs). Artificial Intelligence and Internet of Things, CRC Press. 10.1201/9781003097204-17

[14]

George, M., and Zwiggelaar, R. (2018). Breast tissue classification using Local Binary Pattern variants: A comparative study. Medical Image Understanding and Analysis, Proceedings of the 22nd Conference, MIUA 2018, Southampton, UK, 9–11 July 2018, Springer. Proceedings 22. 10.1007/978-3-319-95921-4_15

[15]

Milton, M.A.A. (2019). Automated skin lesion classification using ensemble of deep neural networks in isic 2018: Skin lesion analysis towards melanoma detection challenge. arXiv.

[16]

Wolner "Enhancing skin cancer diagnosis with dermoscopy" Dermatol. Clin. (2017) 10.1016/j.det.2017.06.003

[17]

Woo, S., Debnath, S., Hu, R., Chen, X., Liu, Z., and Kweon, I.S. (2023, January 17–24). Convnext v2: Co-designing and scaling convnets with masked autoencoders. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada. 10.1109/cvpr52729.2023.01548

[18]

Taufiq, M.A., Hameed, N., Anjum, A., and Hameed, F. (2017). m-Skin Doctor: A mobile enabled system for early melanoma skin cancer detection using support vector machine. eHealth 360°, Proceedings of the International Summit on eHealth, Budapest, Hungary, 14–16 June 2016, Springer. Revised Selected Papers. 10.1007/978-3-319-49655-9_57

[19]

Vidhyalakshmi, A., and Kanchana, M. (2023, January 23–25). AMLGB-: Efficient Model for Skin Disease Detection and Classification using Adaptive Machine for Light Gradient Boosting. Proceedings of the 2023 5th International Conference on Smart Systems and Inventive Technology (ICSSIT), Tirunelveli, India. 10.1109/icssit55814.2023.10060982

[20]

Jaisakthi "Automated skin lesion segmentation of dermoscopic images using GrabCut and k-means algorithms" IET Comput. Vis. (2018) 10.1049/iet-cvi.2018.5289

[21]

Masood, A., Al-Jumaily, A., and Anam, K. (2015, January 22–24). Self-supervised learning model for skin cancer diagnosis. Proceedings of the 2015 7th International IEEE/EMBS Conference on Neural Engineering (NER), Montpellier, France. 10.1109/ner.2015.7146798

[22]

Dermatologist-level classification of skin cancer with deep neural networks

Andre Esteva, Brett Kuprel, Roberto A. Novoa et al.

Nature 2017 10.1038/nature21056

[23]

Nasr-Esfahani, E., Samavi, S., Karimi, N., Soroushmehr, S.M.R., Jafari, M.H., and Ward, K. (2016, January 16–20). Melanoma detection by analysis of clinical images using convolutional neural network. Proceedings of the 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, USA. 10.1109/embc.2016.7590963

[24]

Ghanshala, T., Tripathi, V., and Pant, B. (2021). An efficient image-based skin cancer classification framework using neural network. Research in Intelligent and Computing in Engineering, Springer. 10.1007/978-981-15-7527-3_81

[25]

Hameed "Mobile based skin lesions classification using convolution neural network" Ann. Emerg. Technol. Comput. (AETiC) (2020) 10.33166/aetic.2020.02.003

[26]

Subramanian, R.R., Achuth, D., Kumar, P.S., Reddy, K.N.K., Amara, S., and Chowdary, A.S. (2021, January 28–29). Skin cancer classification using Convolutional neural networks. Proceedings of the 2021 11th International Conference on Cloud Computing, Data Science & Engineering (Confluence), Noida, India. 10.1109/confluence51648.2021.9377155

[27]

Malo, D.C., Rahman, M.M., Mahbub, J., and Khan, M.M. (2022, January 26–29). Skin Cancer Detection using Convolutional Neural Network. Proceedings of the 2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA. 10.1109/ccwc54503.2022.9720751

[28]

Nampalle, K.B., and Raman, B. (2022, January 2–4). An efficient multi-functional deep learning model for effective medical image classification using skin lesion database. Proceedings of the 2022 IEEE 5th International Conference on Multimedia Information Processing and Retrieval (MIPR), Online. 10.1109/mipr54900.2022.00083

[29]

Li, L., and Seo, W. (2021, January 25–27). Deep learning and transfer learning for skin cancer segmentation and classification. Proceedings of the 2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE), Kragujevac, Serbia. 10.1109/bibe52308.2021.9635175

[30]

Agrahari, P., Agrawal, A., and Subhashini, N. (2022). Skin cancer detection using deep learning. Futuristic Communication and Network Technologies: Select Proceedings of VICFCNT 2020, Springer. 10.1007/978-981-16-4625-6_18

[31]

Mnih "Recurrent models of visual attention" Advances in Neural Information Processing Systems 27, Proceedings of the Annual Conference on Neural Information Processing Systems 2014, NIPS, Montreal, QC, Canada, 8–13 December 2014 (2014)

[32]

Bahdanau, D., Cho, K., and Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv.

[33]

Zhu, B., Hofstee, P., Lee, J., and Al-Ars, Z. (2021). An attention module for convolutional neural networks. Artificial Neural Networks and Machine Learning, Proceedings of the ICANN 2021: 30th International Conference on Artificial Neural Networks, Bratislava, Slovakia, 14–17 September 2021, Springer. Proceedings, Part I 30.

[34]

Rensink "The dynamic representation of scenes" Vis. Cogn. (2000) 10.1080/135062800394667

[35]

Control of goal-directed and stimulus-driven attention in the brain

Maurizio Corbetta, Gordon L. Shulman

Nature Reviews Neuroscience 2002 10.1038/nrn755

[36]

Qian, S., Ren, K., Zhang, W., and Ning, H. (2022). Skin lesion classification using CNNs with grouping of multi-scale attention and class-specific loss weighting. Comput. Methods Programs Biomed., 226. 10.1016/j.cmpb.2022.107166

[37]

Singh, H., Devi, K.S., Gaur, S.S., and Bhattacharjee, R. (2023, January 28–30). Automated Skin Cancer Detection using Deep Learning with Self-Attention Mechanism. Proceedings of the 2023 International Conference on Computational Intelligence and Sustainable Engineering Solutions (CISES), Greater Noida, India. 10.1109/cises58720.2023.10183586

[38]

Castro-Fernández, M., Hernández, A., Fabelo, H., Balea-Fernández, F.J., Ortega, S., and Callicó, G.M. (September, January 31). Towards Skin Cancer Self-Monitoring through an Optimized MobileNet with Coordinate Attention. Proceedings of the 2022 25th Euromicro Conference on Digital System Design (DSD), Maspalomas, Spain. 10.1109/dsd57027.2022.00087

[39]

An Effective Skin Cancer Classification Mechanism via Medical Vision Transformer

Suliman Aladhadh, Majed Alsanea, Mohammed Aloraini et al.

Sensors 10.3390/s22114008

[40]

Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022, January 18–24). A convnet for the 2020s. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA. 10.1109/cvpr52688.2022.01167

[41]

Optimized Dual Fire Attention Network and Medium-Scale Fire Classification Benchmark

Hikmat Yar, Tanveer Hussain, Mohit Agarwal et al.

IEEE Transactions on Image Processing 2022 10.1109/tip.2022.3207006

[42]

Yang "Focal modulation networks" Adv. Neural Inf. Process. Syst. (2022)

[43]

Chaturvedi, S.S., Gupta, K., and Prasad, P.S. (2020, January 13–15). Skin lesion analyser: An efficient seven-way multi-class skin cancer classification using mobilenet. Proceedings of the International Conference on Advanced Machine Learning Technologies and Applications, Jaipur, India. 10.1007/978-981-15-3383-9_15

[44]

Huang "Development of a light-weight deep learning model for cloud applications and remote diagnosis of skin cancers" J. Dermatol. (2021) 10.1111/1346-8138.15683

[45]

Shahin, A.H., Kamal, A., and Elattar, M.A. (2018, January 20–22). Deep ensemble learning for skin lesion classification from dermoscopic images. Proceedings of the 2018 9th Cairo International Biomedical Engineering Conference (CIBEC), Cairo, Egypt. 10.1109/cibec.2018.8641815

[46]

Carcagnì, P., Leo, M., Cuna, A., Mazzeo, P.L., Spagnolo, P., Celeste, G., and Distante, C. (2019, January 9–13). Classification of skin lesions by combining multilevel learnings in a DenseNet architecture. Proceedings of the 20th International Conference Image Analysis and Processing (ICIAP 2019), Trento, Italy. 10.1007/978-3-030-30642-7_30

[47]

Chaturvedi "A multi-class skin Cancer classification using deep convolutional neural networks" Multimedia Tools Appl. (2020) 10.1007/s11042-020-09388-2

[48]

Alsunaidi, S.J., Almuhaideb, A.M., Ibrahim, N.M., Shaikh, F.S., Alqudaihi, K.S., Alhaidari, F.A., Khan, I.U., Aslam, N., and Alshahrani, M.S. (2021). Applications of big data analytics to control COVID-19 pandemic. Sensors, 21. 10.3390/s21072282

Metrics

12

Citations

48

References

Details

Published: Jan 22, 2025
Vol/Issue: 15(3)
Pages: 1067
License: View

Authors

S

Su Myat Thwin

Department of Computer Science and Engineering, Ewha Woman’s University, Seoul 03760, Republic of Korea

H

Hyun-Seok Park

Department of Computer Science and Engineering, Ewha Woman’s University, Seoul 03760, Republic of Korea

S

Soo Hyun Seo

Department of Laboratory Medicine, Seoul National University Bundang Hospital, Seongnam 13620, Republic of Korea; Department of Laboratory Medicine, Seoul National University College of Medicine, Seoul 03080, Republic of Korea

Cite This Article

Su Myat Thwin, Hyun-Seok Park, Soo Hyun Seo (2025). A Trustworthy Framework for Skin Cancer Detection Using a CNN with a Modified Attention Mechanism. Applied Sciences, 15(3), 1067. https://doi.org/10.3390/app15031067

A Trustworthy Framework for Skin Cancer Detection Using a CNN with a Modified Attention Mechanism

You May Also Like